Improving Adversarial Robustness of Ensemble Classifiers by Diversified Feature Selection and Stochastic Aggregation

Learning-based classifiers are found to be vulnerable to attacks by adversarial samples. Some works suggested that ensemble classifiers tend to be more robust than single classifiers against evasion attacks. However, recent studies have shown that this is not necessarily the case under more realisti...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Fuyong Zhang, Kuan Li, Ziliang Ren
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	MDPI AG 2024-03-01
Цуврал:	Mathematics
Нөхцлүүд:	adversarial machine learning evasion attacks classifier robustness ensemble classifiers gradient correlation
Онлайн хандалт:	https://www.mdpi.com/2227-7390/12/6/834
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!